{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:VJ4NLE2OT343ZYKUUSGIFHEMFB","short_pith_number":"pith:VJ4NLE2O","schema_version":"1.0","canonical_sha256":"aa78d5934e9ef9bce154a48c829c8c284795e4e509b06719dbdf51b359ab8e45","source":{"kind":"arxiv","id":"1312.5370","version":1},"attestation_state":"computed","paper":{"title":"Perturbed Gibbs Samplers for Synthetic Data Release","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"stat.ML","authors_text":"Joydeep Ghosh, Yubin Park","submitted_at":"2013-12-18T23:16:52Z","abstract_excerpt":"We propose a categorical data synthesizer with a quantifiable disclosure risk. Our algorithm, named Perturbed Gibbs Sampler, can handle high-dimensional categorical data that are often intractable to represent as contingency tables. The algorithm extends a multiple imputation strategy for fully synthetic data by utilizing feature hashing and non-parametric distribution approximations. California Patient Discharge data are used to demonstrate statistical properties of the proposed synthesizing methodology. Marginal and conditional distributions, as well as the coefficients of regression models "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1312.5370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-12-18T23:16:52Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"dea6b6b4018ffd2331b8975437f5cf9bb933804244f064e33d2a2d06a4eb591f","abstract_canon_sha256":"29424af795d3ac40e0cf49dca66e63684444b111cc57e8827bac35adf753fbef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:04:15.006917Z","signature_b64":"fr+6UJ4XwjV6SO53+vMg9+bosZuKoFGJrk1H4VrUSWOlMtvcZy9HqmVuQpUYNq2CeCRaKTWeAJfF09zq37mQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa78d5934e9ef9bce154a48c829c8c284795e4e509b06719dbdf51b359ab8e45","last_reissued_at":"2026-05-18T03:04:15.006441Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:04:15.006441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perturbed Gibbs Samplers for Synthetic Data Release","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"stat.ML","authors_text":"Joydeep Ghosh, Yubin Park","submitted_at":"2013-12-18T23:16:52Z","abstract_excerpt":"We propose a categorical data synthesizer with a quantifiable disclosure risk. Our algorithm, named Perturbed Gibbs Sampler, can handle high-dimensional categorical data that are often intractable to represent as contingency tables. The algorithm extends a multiple imputation strategy for fully synthetic data by utilizing feature hashing and non-parametric distribution approximations. California Patient Discharge data are used to demonstrate statistical properties of the proposed synthesizing methodology. Marginal and conditional distributions, as well as the coefficients of regression models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.5370","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1312.5370","created_at":"2026-05-18T03:04:15.006520+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.5370v1","created_at":"2026-05-18T03:04:15.006520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.5370","created_at":"2026-05-18T03:04:15.006520+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJ4NLE2OT343","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJ4NLE2OT343ZYKU","created_at":"2026-05-18T12:28:04.890932+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJ4NLE2O","created_at":"2026-05-18T12:28:04.890932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJ4NLE2OT343ZYKUUSGIFHEMFB","json":"https://pith.science/pith/VJ4NLE2OT343ZYKUUSGIFHEMFB.json","graph_json":"https://pith.science/api/pith-number/VJ4NLE2OT343ZYKUUSGIFHEMFB/graph.json","events_json":"https://pith.science/api/pith-number/VJ4NLE2OT343ZYKUUSGIFHEMFB/events.json","paper":"https://pith.science/paper/VJ4NLE2O"},"agent_actions":{"view_html":"https://pith.science/pith/VJ4NLE2OT343ZYKUUSGIFHEMFB","download_json":"https://pith.science/pith/VJ4NLE2OT343ZYKUUSGIFHEMFB.json","view_paper":"https://pith.science/paper/VJ4NLE2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.5370&json=true","fetch_graph":"https://pith.science/api/pith-number/VJ4NLE2OT343ZYKUUSGIFHEMFB/graph.json","fetch_events":"https://pith.science/api/pith-number/VJ4NLE2OT343ZYKUUSGIFHEMFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJ4NLE2OT343ZYKUUSGIFHEMFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJ4NLE2OT343ZYKUUSGIFHEMFB/action/storage_attestation","attest_author":"https://pith.science/pith/VJ4NLE2OT343ZYKUUSGIFHEMFB/action/author_attestation","sign_citation":"https://pith.science/pith/VJ4NLE2OT343ZYKUUSGIFHEMFB/action/citation_signature","submit_replication":"https://pith.science/pith/VJ4NLE2OT343ZYKUUSGIFHEMFB/action/replication_record"}},"created_at":"2026-05-18T03:04:15.006520+00:00","updated_at":"2026-05-18T03:04:15.006520+00:00"}